feat: introduce mlp implementation for gated FFN (swiglu, ...)#943
Open
feat: introduce mlp implementation for gated FFN (swiglu, ...)#943
Conversation
Member
|
This PR looks good to me. I'm happy to approve it once it has been rebased and the integration tests are passing! |
Member
|
@ssmmnn11 it's a great contribution. It would be valuable to add some scientific results to support this great work. |
# Conflicts: # models/src/anemoi/models/layers/processor.py # models/tests/layers/block/test_block_transformer.py # training/src/anemoi/training/train/train.py
# Conflicts: # models/src/anemoi/models/layers/mapper.py # models/src/anemoi/models/layers/processor.py # models/src/anemoi/models/schemas/common_components.py # models/tests/layers/block/test_block_graphtransformer.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Introduce mlp_implementation (mlp, glu, swiglu, geglu, reglu) for Transformer, GraphTransformer, and GNN
breaking change: FFN state_dict key names changed (mlp.* -> mlp.mlp.*),
PointWiseMLPProcessor unchanged